Abstraction, Reasoning and Deep Learning: A Study of the "Look and Say" Sequence
원문 초록
The ability to abstract, count, and use System~2 reasoning are well-known manifestations of intelligence and understanding. In this paper, we argue, using the example of the ``Look and Say" puzzle, that although deep neural networks can exhibit high `competence' (as measured by accuracy) when trained on large data sets (2 million examples in our case), they do not show any sign on the deeper understanding of the problem, or what D. Dennett calls `comprehension'. We report on two sets experiments: first, computing the next element of the sequence, and ,then, the previous element. We view both problems as building a translator from one set of tokens to another. We apply both standard LSTMs and Transformer/Attention-based neural networks, using publicly available machine translation software. We observe that despite the amazing accuracy, the performance of the trained programs on the actual L\&S sequence is bad, and shows no understanding of the principles behind the sequences. The ramifications of this finding include: (1) from the cognitive science perspective, we argue that we need better mathematical models of abstraction; (2) the universality of neural networks should be re-examined for functions acting on discrete data sets; (3) we hypothesize topology can provide a definition of without the reference to the concept of distance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Has Machine Translation Evaluation Achieved Human Parity? The Human Reference and the Limits of Progress
CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation
ConsistencyChecker: Tree-based Evaluation of LLM Generalization Capabilities
Deep Symmetric Autoencoders from the Eckart-Young-Schmidt Perspective
Gender Bias in English-to-Greek Machine Translation
TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration
토론
이 논문과 연결된 포럼 글이 아직 없습니다.